Method and Device for Detecting Safe Driving State of Driver

Abstract

Disclosure is a method for detecting the safety driving state of a driver, the method comprises the following steps: (a) detecting the current sight direction of a driver in real time and acquiring a scene image signal in a front view field of the driver when a vehicle runs; (b) processing the acquired current road scene image signal according to a visual attention calculation model to obtain the expected attention distribution of the driver under the current road scene; and (c) performing fusion analysis on the real-time detected current sight direction of the driver in the step (a) and the calculated expected attention distribution of the driver in step (b), and judging whether the current driver is in a normal driving state and whether the driver can timely make a proper response to the sudden road traffic accident. The device is used for implementing the method and has the advantages of simple principle, easy realization, direct reflection of the real driving state of a driver, and improvement of the driving safety.

Description

NOTICE OF COPYRIGHT[0001]A portion of the disclosure of this patent document contains material which is subject to copyright protection. The copyright owner has no objection to any reproduction by anyone of the patent disclosure, as it appears in the United States Patent and Trademark Office patent files or records, but otherwise reserves all copyright rights whatsoever.BACKGROUND OF THE PRESENT INVENTION[0002]Field of Invention[0003]The present invention mainly relates to the field of vehicular active safety design, and particularly relates to a method and a device for detecting the safety driving state of a driver.[0004]Description of Related Arts[0005]With the development of vehicle industry, vehicles have increasingly become an important part of social production and daily life; meanwhile, vehicle safety also gradually becomes a focus of attention. According to the statistics, about 75% of road traffic accidents are caused by human errors, namely caused by personal factors of dr...

AI Technical Summary

Benefits of technology

[0012]Technical problems to be solved by the present invention lie in that aiming at the technical problems of the prior art, the present invention provides a method and a device for detecting the safety driving state of a driver, which are simple in principle and easy to implement and can directly reflect the real driving state of the driver and improve the driving safety.

[0041]Compared with the prior art, the present invention has the following advantages:

[0043]2. In the present invention, abnormal driving states caused by fatigue of drivers can be detected, unsafe driving states such as distraction, other event's attraction and the like in non-fatigue states of drivers, as well as unsafe states such as slow response caused by taking some drugs, drinking too much wine, lacking driving experience and the like, so that the overall safety is greatly improved.

[0045]4. The detection result of the present invention is more accurate. Because the driving state of a driver is not indirectly judged by using the fatigue state or the response of the driver to specific events, the detection result can reflect the judging and processing abilities of the driver on the current road traffic accident. In the normal driving state, the driver is bound to allocate and pay the attention to a remarkable area in the current road scene, so the driving state of the driver can be effectively estimated by comparing the actual attention with the expected attention. Meanwhile, both the actual measurement on the attention of the driver and the calculation on the scene attention have very high precision, so the mental state of the driver can be accurately judged.

Problems solved by technology

Specifically, the personal factors include inaccurate estimation of drivers on vehicle running environments, response lag of drivers and the like.

The working principle of the detection method based on physical fatigue characteristics of a driver is based on a basic assumption: when the mental state of a driver is poor, the driving state is also poor, so the driver cannot safely accomplish the driving task.

In conclusion, the method for deducing the safety driving state of the driver from the fatigue state of the driver has the problems of the following three aspects: I, the method is an indirect detection method with unreliable effect: it is difficult to give a direct corresponding relation between the fatigue state and the safety of the driving behavior of the driver by merely taking the fatigue state of the driver as the detection means of the safety driving state of the driver, and it is uncertain that fatigue is judged by external physical characteristics; II, deducing whether the driving state of the driver is safe or not from the fatigue state is limited to unsafe state detection: the driver in an unsafe driving state is not always in a fatigue state; and III, it is difficult to ensure the timeliness when whether the driving state of the driver is safe or not is deduced from the fatigue state is adopted: when the driver is in a fatigue state, the driving behavior is quite unsafe.

The method has the defects of I, a judgment is generally given at an impending dangerous traffic accident; and II, it is difficult to definitely and objectively judge normal traffic accidents and abnormal traffic accidents, e.g., normal overtaking lane-crossing behavior and abnormal lane departure behavior.

For example, drivers have insufficient experience and poor driving habits, new learners are too tense and do not notice traffic accidents which should be noticed.

The existing detection technologies for the safety driving state of a driver are difficult in detecting the second type of unsafe driving states.

If the driver cannot make a quick response to instant important traffic accidents, the driver is in a dangerous or abnormal driving state.

Images